def form_restart_pipeline_process(pipeline_type):
'''
Restart a pipeline process from the last step ended OK.
'''
# initialize the control variable
OK = True
# set the pipeline name
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
name = xlib.get_toa_process_pipeline_nucleotide_name()
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
name = xlib.get_toa_process_pipeline_aminoacid_name()
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'{name} - Run process')
# get the pipeline dataset identification
app_list = [pipeline_type]
pipeline_dataset_id = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id == '':
print(f'WARNING: There are not any {pipeline_type} result datasets.')
OK = False
# confirm the process run
if OK:
print(xlib.get_separator())
OK = clib.confirm_action(f'The {name} process is going to be run.')
# run the process
if OK:
devstdout = xlib.DevStdOut(xtoa.restart_pipeline_process.__name__)
OK = xtoa.restart_pipeline_process(pipeline_type,
pipeline_dataset_id,
devstdout,
function=None)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_view_phylogenic_data_frecuency(stats_code):
'''
View the frecuency distribution of phylogenic data.
'''
# initialize the control variable
OK = True
# assign the text of the "name"
if stats_code == 'species':
name = 'Species - Frequency distribution'
elif stats_code == 'family':
name = 'Family - Frequency distribution'
elif stats_code == 'phylum':
name = 'Phylum - Frequency distribution'
elif stats_code == 'namespace':
name = 'GO - Frequency distribution per namespace'
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'Statistics - {name} data')
# get the pipeline dataset identification
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code(),
xlib.get_toa_process_merge_annotations_code()
]
pipeline_dataset_id = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id == '':
print(
'WARNING: There are not any annotation pipeline result datasets.')
OK = False
# build distribution dictionary
if OK:
# initialize the distribution dictionary
distribution_dict = {}
# get the dictionary of TOA configuration
toa_config_dict = xtoa.get_toa_config_dict()
# get the statistics file path
stats_file = f'{toa_config_dict["RESULT_DIR"]}/{xlib.get_toa_result_pipeline_dir()}/{pipeline_dataset_id}/{toa_config_dict["STATS_SUBDIR_NAME"]}/{stats_code}-{toa_config_dict["STATS_BASE_NAME"]}.csv'
# open the statistics file
if stats_file.endswith('.gz'):
try:
stats_file_id = gzip.open(stats_file,
mode='rt',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F002', stats_file)
else:
try:
stats_file_id = open(stats_file,
mode='r',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F001', stats_file)
# initialize the record counter
record_counter = 0
# initialize the header record control
header_record = True
# read the first record
record = stats_file_id.readline()
# while there are records
while record != '':
# add 1 to the record counter
record_counter += 1
# process the header record
if header_record:
header_record = False
# process data records
else:
# extract data
# record format: "stats_code_id";"all_count";"first_hsp_count";"min_evalue_count"
data_list = []
begin = 0
for end in [i for i, chr in enumerate(record) if chr == ';']:
data_list.append(record[begin:end].strip('"'))
begin = end + 1
data_list.append(record[begin:].strip('\n').strip('"'))
try:
id = data_list[0]
all_count = data_list[1]
first_hsp_count = data_list[2]
min_evalue_count = data_list[3]
except Exception as e:
raise xlib.ProgramException('F006',
os.path.basename(stats_file),
record_counter)
# add dato to the dictionary
distribution_dict[id] = {
'id': id,
'all_count': all_count,
'first_hsp_count': first_hsp_count,
'min_evalue_count': min_evalue_count
}
# read the next record
record = stats_file_id.readline()
# print the distribution
if OK:
print(xlib.get_separator())
if distribution_dict == {}:
print('*** WARNING: There is not any distribution.')
else:
# set data width
id_width = 50
all_count_width = 11
first_hsp_count_width = 11
min_evalue_count_width = 11
# set line template
line_template = '{0:' + str(id_width) + '} {1:' + str(
all_count_width) + '} {2:' + str(
first_hsp_count_width) + '} {3:' + str(
min_evalue_count_width) + '}'
# print header
print(
line_template.format(stats_code.capitalize(), 'All',
'First HSP', 'Min e-value'))
print(
line_template.format('=' * id_width, '=' * all_count_width,
'=' * first_hsp_count_width,
'=' * min_evalue_count_width))
# print detail lines
for key in sorted(distribution_dict.keys()):
print(
line_template.format(
distribution_dict[key]['id'],
distribution_dict[key]['all_count'],
distribution_dict[key]['first_hsp_count'],
distribution_dict[key]['min_evalue_count']))
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_view_dataset_data_frecuency():
'''
View the frecuency distribution of annotation dataset data.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment(
'Statistics - Annotation datasets - Frequency distribution data')
# get the pipeline dataset identification
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code()
]
pipeline_dataset_id = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id == '':
print(
'WARNING: There are not any annotation pipeline result datasets.')
OK = False
# build distribution dictionary
if OK:
# initialize the distribution dictionary
distribution_dict = {}
# get the dictionary of TOA configuration
toa_config_dict = xtoa.get_toa_config_dict()
# get the statistics file path
stats_file = f'{toa_config_dict["RESULT_DIR"]}/{xlib.get_toa_result_pipeline_dir()}/{pipeline_dataset_id}/{toa_config_dict["STATS_SUBDIR_NAME"]}/dataset-{toa_config_dict["STATS_BASE_NAME"]}.csv'
# open the statistics file
if stats_file.endswith('.gz'):
try:
stats_file_id = gzip.open(stats_file,
mode='rt',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F002', stats_file)
else:
try:
stats_file_id = open(stats_file,
mode='r',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F001', stats_file)
# initialize the record counter
record_counter = 0
# initialize the header record control
header_record = True
# read the first record
record = stats_file_id.readline()
# while there are records
while record != '':
# add 1 to the record counter
record_counter += 1
# process the header record
if header_record:
header_record = False
# process data records
else:
# extract data
# record format: "dataset_name";"annotated_seq_count";"remained_seq_count"
data_list = []
begin = 0
for end in [i for i, chr in enumerate(record) if chr == ';']:
data_list.append(record[begin:end].strip('"'))
begin = end + 1
data_list.append(record[begin:].strip('\n').strip('"'))
try:
dataset_name = data_list[0]
annotated_seq_count = data_list[1]
remained_seq_count = data_list[2]
except Exception as e:
raise xlib.ProgramException('F006',
os.path.basename(stats_file),
record_counter)
# add dato to the dictionary
distribution_dict[record_counter] = {
'dataset_name': dataset_name,
'annotated_seq_count': annotated_seq_count,
'remained_seq_count': remained_seq_count
}
# read the next record
record = stats_file_id.readline()
# print the distribution
if OK:
print(xlib.get_separator())
if distribution_dict == {}:
print('*** WARNING: There is not any distribution.')
else:
# set data width
dataset_name_width = 19
annotated_seq_count_width = 14
remained_seq_count_width = 14
# set line template
line_template = '{0:' + str(dataset_name_width) + '} {1:' + str(
annotated_seq_count_width) + '} {2:' + str(
remained_seq_count_width) + '}'
# print header
print(
line_template.format('Dataset', 'Annotated seqs',
'Remained seqs'))
print(
line_template.format('=' * dataset_name_width,
'=' * annotated_seq_count_width,
'=' * remained_seq_count_width))
# print detail lines
for key in sorted(distribution_dict.keys()):
print(
line_template.format(
distribution_dict[key]['dataset_name'],
distribution_dict[key]['annotated_seq_count'],
distribution_dict[key]['remained_seq_count']))
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_view_x_per_y_data(stats_code):
'''
View the x per y data.
'''
# initialize the control variable
OK = True
# assign the text of the "name"
if stats_code == 'hit_per_hsp':
name = '# HITs per # HSPs'
elif stats_code == 'seq_per_go':
name = '# sequences per # GO terms'
elif stats_code == 'seq_per_ec':
name = '# sequences per # EC ids'
elif stats_code == 'seq_per_interpro':
name = '# sequences per # InterPro ids'
elif stats_code == 'seq_per_kegg':
name = '# sequences per # KEGG ids'
elif stats_code == 'seq_per_mapman':
name = '# sequences per # MapMan ids'
elif stats_code == 'seq_per_metacyc':
name = '# sequences per # MetaCyc ids'
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'Statistics - {name} data')
# get the pipeline dataset identification
if stats_code == 'hit_per_hsp':
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code()
]
else:
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code(),
xlib.get_toa_process_merge_annotations_code()
]
pipeline_dataset_id = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id == '':
print(
'WARNING: There are not any annotation pipeline result datasets.')
OK = False
# build distribution dictionary
if OK:
# initialize the distribution dictionary
distribution_dict = {}
# get the dictionary of TOA configuration
toa_config_dict = xtoa.get_toa_config_dict()
# get the statistics file path
stats_file = f'{toa_config_dict["RESULT_DIR"]}/{xlib.get_toa_result_pipeline_dir()}/{pipeline_dataset_id}/{toa_config_dict["STATS_SUBDIR_NAME"]}/{stats_code}-{toa_config_dict["STATS_BASE_NAME"]}.csv'
# open the statistics file
if stats_file.endswith('.gz'):
try:
stats_file_id = gzip.open(stats_file,
mode='rt',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F002', stats_file)
else:
try:
stats_file_id = open(stats_file,
mode='r',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F001', stats_file)
# initialize the record counter
record_counter = 0
# initialize the header record control
header_record = True
# read the first record
record = stats_file_id.readline()
# while there are records
while record != '':
# add 1 to the record counter
record_counter += 1
# process the header record
if header_record:
header_record = False
# process data records
else:
# extract data
# record format: "x_count";"y_count"
data_list = []
begin = 0
for end in [i for i, chr in enumerate(record) if chr == ';']:
data_list.append(record[begin:end].strip('"'))
begin = end + 1
data_list.append(record[begin:].strip('\n').strip('"'))
try:
x_count = data_list[0]
y_count = data_list[1]
except Exception as e:
raise xlib.ProgramException('F006',
os.path.basename(stats_file),
record_counter)
# add dato to the dictionary
distribution_dict[record_counter] = {
'x_count': x_count,
'y_count': y_count
}
# read the next record
record = stats_file_id.readline()
# print the distribution
if OK:
print(xlib.get_separator())
if distribution_dict == {}:
print('*** WARNING: There is not any stats data.')
else:
# set data width
x_count_width = 15
y_count_width = 15
# set line template
line_template = '{0:' + str(x_count_width) + '} {1:' + str(
y_count_width) + '}'
# print header
if stats_code == 'hit_per_hsp':
print(line_template.format('# HSPs', '# HITs'))
elif stats_code == 'seq_per_go':
print(line_template.format('# GO terms', '# sequences'))
elif stats_code == 'seq_per_ec':
print(line_template.format('# EC ids', '# sequences'))
elif stats_code == 'seq_per_interpro':
print(line_template.format('# InterPro ids', '# sequences'))
elif stats_code == 'seq_per_kegg':
print(line_template.format('# KEGG ids', '# sequences'))
elif stats_code == 'seq_per_mapman':
print(line_template.format('# MapMan ids', '# sequences'))
elif stats_code == 'seq_per_metacyc':
print(line_template.format('# MetaCyc ids', '# sequences'))
print(
line_template.format('=' * x_count_width, '=' * y_count_width))
# print detail lines
for key in sorted(distribution_dict.keys()):
print(
line_template.format(distribution_dict[key]['x_count'],
distribution_dict[key]['y_count']))
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_recreate_annotation_merger_config_file():
'''
Recreate the annotation merger config file.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment(
f'{xlib.get_toa_process_merge_annotations_name()} - Recreate config file'
)
# get the identification of the first pipeline dataset
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code(),
xlib.get_toa_process_merge_annotations_code()
]
print('First pipeline ...')
pipeline_dataset_id_1 = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id_1 == '':
print('WARNING: There are not any pipeline datasets.')
OK = False
# get the identification of the second pipeline dataset
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code(),
xlib.get_toa_process_merge_annotations_code()
]
print('Second pipeline ...')
pipeline_dataset_id_2 = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id_2 == '':
print('WARNING: There are not any pipeline datasets.')
OK = False
elif pipeline_dataset_id_1 == pipeline_dataset_id_2:
print('ERROR: The first pipeline dataset is equal to the second one.')
OK = False
# get the merger operation
if OK:
merger_operation = cinputs.input_code(
text='Merger operation',
code_list=xlib.get_annotation_merger_operation_code_list(),
default_code=None).upper()
# recreate the pipeline config file
if OK:
# confirm the creation of the config file
print(xlib.get_separator())
OK = clib.confirm_action(
f'The file {xtoa.get_annotation_merger_config_file()} is going to be recreated. The previous files will be lost.'
)
# recreate the config file
if OK:
(OK, error_list) = xtoa.create_annotation_merger_config_file(
pipeline_dataset_id_1, pipeline_dataset_id_2, merger_operation)
if OK:
print('The file is recreated.')
else:
for error in error_list:
print(error)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')